skills/design-doc/SKILL.md
Write a lightweight design doc before implementation for Medium/Large tasks. Mandates Non-Goals and Alternatives Considered sections to prevent scope creep and hindsight bias. Inspired by Google design doc culture.
npx skillsauth add the-own-lab/Claude-company-of-one design-docInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write before you build. A solo founder's worst enemy is scope creep and hindsight drift — a design doc fixes the scope in writing so you can notice when you're wandering.
What is broken or missing? Write it so someone who doesn't know the task context can follow. 2–4 sentences.
The approach you intend to take. Bullet points are fine. Include any data shapes, key flows, or interfaces.
Mandatory. Things this work explicitly will NOT do. This section exists to bound scope.
Mandatory. At least 2 alternatives, each with one-line "why rejected."
Things you don't know yet. Flag them so review surfaces them early.
write-plan (design → plan → execute)${COMPANY_OF_ONE_PLUGIN_DATA}/projects/{key}/specs/ for Large taskssuccess-metric skill output into section 1 (Problem) to tie design to measurable outcomedocumentation
Update BRIEF.md sections during a command run. Any skill that produces a brief-persisted artifact calls this to write it back.
development
Post-code check: run tests + confirm TODO acceptance items map to passing tests; applies a security lens but is not a separate scan.
documentation
Command post-step: write CHANGELOG + TODO once per command run. One call, not per-skill doc writes.
content-media
Author REQUIREMENTS.md + DESIGN.md + TODO.md for a feature. The three files are one contract; they ship together.